Cleanup artifacts

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description claims a delete operation ('Removes ... files'), which is a destructive update, while the annotation declares destructiveHint=false. That inconsistency is a serious mismatch. Beyond the mismatch, the description says nothing about permanence, recursion, git-tracking, or confirmation behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One short sentence, front-loaded with the verb and scope, with no filler. It is efficient, though arguably too terse for a deletion tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool that deletes files, with no output schema and only annotations for structure, the definition omits what qualifies as an artifact, whether deletion is recursive or recoverable, and what is returned. The single sentence is not complete enough for the risk profile.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the burden. It only implies that target_dir is a directory path ('the specified directory'), which the parameter name already conveys, and adds no format, relative/absolute path, or recursion semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb ('Removes') and resource ('test artifacts and temporary files') scoped to 'the specified directory', so the agent knows exactly what operation it is. It does not, however, differentiate itself from nearby cleanup-style siblings such as rm_build_gc, rm_worktree_prune, or rm_worktree_remove.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use, when-not-to-use, or prerequisite guidance is given. The agent must infer that cleanup is appropriate from the name alone, and no alternative cleanup tool is referenced.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.